© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 105196
    Prev
    Next
    INDEX
    Explanations

    catastrophic or cataphracts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_1_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '
    1.34
    lere
    1.22
    languages
    1.16
    lok
    1.14
    ↵
    1.13
    lara
    1.11
    ians
    1.10
    lains
    1.09
    lık
    1.08
    labor
    1.08
    POSITIVE LOGITS
    й
    1.33
    ﺍ
    1.28
     و
    1.27
    ル
    1.24
    не
    1.22
    з
    1.20
     prennent
    1.18
    л
    1.16
    ک
    1.11
     ও
    1.09
    Activations Density 0.002%

    No Known Activations